© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 4805
    Prev
    Next
    INDEX
    Explanations

    scroll left to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_39_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    getPackageName
    0.34
     montée
    0.33
     মহল
    0.30
     rte
    0.27
     remix
    0.27
     स्‍ट
    0.27
     remixes
    0.26
    ୀ
    0.26
     nl
    0.26
     rise
    0.26
    POSITIVE LOGITS
    往下
    0.30
     Visibility
    0.30
    Visibility
    0.30
     visibility
    0.29
     Thumb
    0.29
     Invisible
    0.29
     पुत्र
    0.28
     Bottom
    0.28
    idders
    0.28
    Thumb
    0.28
    Activations Density 0.006%

    No Known Activations